@inproceedings{4898809f0c6f486c9361aae078498773,
title = "Yet Another Model for Arabic Dialect Identification",
abstract = "In this paper, we describe a spoken Arabic dialect identification (ADI) model for Arabic that consistently outperforms previously published results on two benchmark datasets: ADI-5 and ADI-17. We explore two architectural variations: ResNet and ECAPA-TDNN, coupled with two types of acoustic features: MFCCs and features exratected from the pre-trained self-supervised model UniSpeech-SAT Large, as well as a fusion of all four variants. We find that individually, ECAPA-TDNN network outperforms ResNet, and models with UniSpeech-SAT features outperform models with MFCCs by a large margin. Furthermore, a fusion of all four variants consistently outperforms individual models. Our best models outperform previously reported results on both datasets, with accuracies of 84.7% and 96.9% on ADI-5 and ADI-17, respectively.",
author = "Ajinkya Kulkarni and Hanan Aldarmaki",
note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 1st Arabic Natural Language Processing Conference, ArabicNLP 2023 ; Conference date: 07-12-2023",
year = "2023",
language = "English",
series = "ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "435--440",
editor = "Hassan Sawaf and Samhaa El-Beltagy and Wajdi Zaghouani and Walid Magdy and Nadi Tomeh and {Abu Farha}, Ibrahim and Nizar Habash and Salam Khalifa and Amr Keleg and Hatem Haddad and Imed Zitouni and Ahmed Abdelali and Khalil Mrini and Rawan Almatham",
booktitle = "ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Porceedings",
address = "United States",
}